Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 7729
    Prev
    Next
    INDEX
    Explanations

    physical objects or parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    0.58
    q
    0.47
    지
    0.43
    the
    0.38
    :
    0.38
    ༦
    0.36
    یل
    0.36
    きた
    0.36
    9
    0.35
    se
    0.35
    POSITIVE LOGITS
     Kollegen
    0.41
     Existe
    0.40
    andowski
    0.39
     Nachricht
    0.38
     Ciências
    0.38
    '
    0.38
     Plugins
    0.38
     for
    0.37
    iatura
    0.37
    ot
    0.37
    Activations Density 0.676%

    No Known Activations